porter-five-forces
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from existing documents when performing updates or searches, which could allow instructions embedded in those documents to influence the agent.
- Ingestion points: Reads local markdown files from paths including strategy/, research/, competitive/, and analysis/, as well as user-provided paths (SKILL.md).
- Boundary markers: There are no explicit instructions for the agent to isolate, delimit, or ignore embedded instructions within the ingested documents (SKILL.md).
- Capability inventory: The skill leverages WebSearch for data gathering and has file-read and file-write capabilities to manage analysis outputs (SKILL.md).
- Sanitization: No validation, escaping, or sanitization of the input file content is specified before processing (SKILL.md).
Audit Metadata